Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland
Deep learning has already been proved as a powerful state-of-the-art technique for many image understanding tasks in computer vision and other applications including remote sensing (RS) image analysis. Unmanned aircraft systems (UASs) offer a viable and economical alternative to a conventional senso...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/6/959 |
| _version_ | 1798027075343351808 |
|---|---|
| author | Mohammad Pashaei Hamid Kamangir Michael J. Starek Philippe Tissot |
| author_facet | Mohammad Pashaei Hamid Kamangir Michael J. Starek Philippe Tissot |
| author_sort | Mohammad Pashaei |
| collection | DOAJ |
| description | Deep learning has already been proved as a powerful state-of-the-art technique for many image understanding tasks in computer vision and other applications including remote sensing (RS) image analysis. Unmanned aircraft systems (UASs) offer a viable and economical alternative to a conventional sensor and platform for acquiring high spatial and high temporal resolution data with high operational flexibility. Coastal wetlands are among some of the most challenging and complex ecosystems for land cover prediction and mapping tasks because land cover targets often show high intra-class and low inter-class variances. In recent years, several deep convolutional neural network (CNN) architectures have been proposed for pixel-wise image labeling, commonly called semantic image segmentation. In this paper, some of the more recent deep CNN architectures proposed for semantic image segmentation are reviewed, and each model’s training efficiency and classification performance are evaluated by training it on a limited labeled image set. Training samples are provided using the hyper-spatial resolution UAS imagery over a wetland area and the required ground truth images are prepared by manual image labeling. Experimental results demonstrate that deep CNNs have a great potential for accurate land cover prediction task using UAS hyper-spatial resolution images. Some simple deep learning architectures perform comparable or even better than complex and very deep architectures with remarkably fewer training epochs. This performance is especially valuable when limited training samples are available, which is a common case in most RS applications. |
| first_indexed | 2024-04-11T18:46:34Z |
| format | Article |
| id | doaj.art-ac621b5f94f54b1d8c5927d9d63583ce |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T18:46:34Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ac621b5f94f54b1d8c5927d9d63583ce2022-12-22T04:08:48ZengMDPI AGRemote Sensing2072-42922020-03-0112695910.3390/rs12060959rs12060959Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a WetlandMohammad Pashaei0Hamid Kamangir1Michael J. Starek2Philippe Tissot3Department of Computing Sciences, Texas A&M University-Corpus Christi, Corpus Christi, TX 78412, USADepartment of Computing Sciences, Texas A&M University-Corpus Christi, Corpus Christi, TX 78412, USADepartment of Computing Sciences, Texas A&M University-Corpus Christi, Corpus Christi, TX 78412, USAConrad Blucher Institute for Surveying and Science, Texas A&M University-Corpus Christi, Corpus Christi, TX 78412, USADeep learning has already been proved as a powerful state-of-the-art technique for many image understanding tasks in computer vision and other applications including remote sensing (RS) image analysis. Unmanned aircraft systems (UASs) offer a viable and economical alternative to a conventional sensor and platform for acquiring high spatial and high temporal resolution data with high operational flexibility. Coastal wetlands are among some of the most challenging and complex ecosystems for land cover prediction and mapping tasks because land cover targets often show high intra-class and low inter-class variances. In recent years, several deep convolutional neural network (CNN) architectures have been proposed for pixel-wise image labeling, commonly called semantic image segmentation. In this paper, some of the more recent deep CNN architectures proposed for semantic image segmentation are reviewed, and each model’s training efficiency and classification performance are evaluated by training it on a limited labeled image set. Training samples are provided using the hyper-spatial resolution UAS imagery over a wetland area and the required ground truth images are prepared by manual image labeling. Experimental results demonstrate that deep CNNs have a great potential for accurate land cover prediction task using UAS hyper-spatial resolution images. Some simple deep learning architectures perform comparable or even better than complex and very deep architectures with remarkably fewer training epochs. This performance is especially valuable when limited training samples are available, which is a common case in most RS applications.https://www.mdpi.com/2072-4292/12/6/959coastal wetlandland cover mappingsemantic image segmentationmachine learningdeep learningconvolutional neural networkstransfer learningunmanned aircraft systems |
| spellingShingle | Mohammad Pashaei Hamid Kamangir Michael J. Starek Philippe Tissot Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland Remote Sensing coastal wetland land cover mapping semantic image segmentation machine learning deep learning convolutional neural networks transfer learning unmanned aircraft systems |
| title | Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland |
| title_full | Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland |
| title_fullStr | Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland |
| title_full_unstemmed | Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland |
| title_short | Review and Evaluation of Deep Learning Architectures for Efficient Land Cover Mapping with UAS Hyper-Spatial Imagery: A Case Study Over a Wetland |
| title_sort | review and evaluation of deep learning architectures for efficient land cover mapping with uas hyper spatial imagery a case study over a wetland |
| topic | coastal wetland land cover mapping semantic image segmentation machine learning deep learning convolutional neural networks transfer learning unmanned aircraft systems |
| url | https://www.mdpi.com/2072-4292/12/6/959 |
| work_keys_str_mv | AT mohammadpashaei reviewandevaluationofdeeplearningarchitecturesforefficientlandcovermappingwithuashyperspatialimageryacasestudyoverawetland AT hamidkamangir reviewandevaluationofdeeplearningarchitecturesforefficientlandcovermappingwithuashyperspatialimageryacasestudyoverawetland AT michaeljstarek reviewandevaluationofdeeplearningarchitecturesforefficientlandcovermappingwithuashyperspatialimageryacasestudyoverawetland AT philippetissot reviewandevaluationofdeeplearningarchitecturesforefficientlandcovermappingwithuashyperspatialimageryacasestudyoverawetland |